Reply to Abrantes et al. Recombination-Based Perspectives on Lagovirus Classification, Phylogenetic Patterns, and Evolutionary Dynamics. Comment on "Shah et al. Genetic Characteristics and Phylogeographic Dynamics of Lagoviruses, 1988-2021. Viruses 2023, 15, 815".

Recently, Abrantes et al [...].

Insights into the genetic characteristics, clustering patterns, and phylogeographic dynamics of the JC polyomavirus, 1993 to 2023.

The human JC polyomavirus (JCV) is a widespread, neurotropic, opportunistic pathogen responsible for progressive multifocal leukoencephalopathy (PML) as well as other diseases in immunosuppressed individuals, including granule cell neuronopathy, JCV-associated nephropathy, encephalitis, and meningitis in rare cases. JCV classification is still unclear, where the ICTV (International Committee on Taxonomy of Viruses) has grouped all the strains into human polyomavirus 2, with no classification on clade and subclade levels. Therefore, JCV strains were previously classified using different genomic regions, e.g., full-length, VP1, and the V-T intergenic region etc., and the strains were grouped into several types related to various geographic locations and human ethnicities. However, neither of these classifications and nomenclature contemplates all the groups described so far. Herein, we evaluated all the available full-length coding genomes, VP1, and large T antigen nucleotide sequences of JCV reported during 1993-2023 and classified them into four major phylogenetic clades, i.e., GI-GIV, where GI is further grouped into two types GI.1 and GI.2 with five sub-clades each (GI.1/GI.2 a-e), GII into three (GII a-c), GIII as a separate clade, and GIV into seven sub-clades (GIV a-g). Similarly, the phylogeographic network analysis indicated four major clusters corresponding to GI-GIV clades, each with multiple subclusters and mutational sub-branches corresponding to the subclades. GI and GIV clusters are connected via GI.1-e reported from Europe and America, GII, GIII and GIV clusters are connected by GII-b and GII-c strains reported from Africa, while GIV cluster strains are connected to the Russia-Italy JCV haplotype. Furthermore, we identified JCV-variant-GS/B-Germany-1997 (GenBank ID: AF004350.1) as an inter-genotype recombinant having major and minor parents in the GI.1-e and GII-a clades, respectively. Additionally, the amino acid variability analysis revealed high entropy across all proteins. The large T antigen exhibited the highest variability, while the small t antigen showed the lowest variability. Our phylogenetic and phylogeographic analyses provide a new approach to genotyping and sub-genotyping and present a comprehensive classification system of JCV strains based on their genetic characteristics and geographic distribution, while the genetic recombination and amino acid variability can help identify pathogenicity and develop effective preventive and control measures against JCV infections.

Genetic diversity and phylogeographic dynamics of avihepadnavirus: a comprehensive full-length genomic view.

Avihepadnavirus is a genus of the Hepadnaviridae family. It primarily infects birds, including species of duck, geese, cranes, storks, and herons etc. To understand the genetic relatedness and evolutionary diversity among avihepadnavirus strains, a comprehensive analysis of the available 136 full-length viral genomes (n = 136) was conducted. The genomes were classified into two major genotypes, i.e., GI and GII. GI viruses were further classified into 8 sub-genotypes including DHBV-I (duck hepatitis B virus-I), DHBV-II (Snow goose Hepatitis B, SGHBV), DHBV-III, RGHBV (rossgoose hepatitis B virus), CHBV (crane hepatitis B virus), THBV (Tinamou hepatitis B virus), STHBV (stork hepatitis B virus), and HHBV (Heron hepatitis B virus). DHBV-I contains two sub-clades DHBV-Ia and DHBV-Ib. Parrot hepatitis B virus (PHBV) stains fall into GII which appeared as a separate phylogenetic branch/clade. All the subtypes of viruses in GI and GII seem to be genetically connected with viruses of DHBV-I by multiple mutational steps in phylogeographic analysis. Furthermore, 16 potential recombination events among different sub-genotypes in GI and one in GII were identified, but none of which is inter-genotypic between GI and GII. Overall, the results provide a whole picture of the genetic relatedness of avihepadnavirus strains, which may assist in the surveillance of virus spreading.

Immune-Escape Mutations Are Prevalent among Patients with a Coexistence of HBsAg and Anti-HBs in a Tertiary Liver Center in the United States.

The concurrent seropositivity of HBsAg and anti-HBs has been described among patients with chronic hepatitis B (CHB), but its prevalence is variable. HBV S-gene mutations can affect the antigenicity of HBsAg. Patients with mutations in the 'α' determinant region of the S gene can develop severe HBV reactivation under immunosuppression. In this study at a tertiary liver center in the United States, we evaluated the frequency and virological characteristics of the HBsAg mutations among CHB patients with the presence of both HBsAg and anti-HBs. In this cohort, 45 (2.1%) of 2178 patients were identified to have a coexistence of HBsAg and anti-HBs, and 24 had available sera for the genome analysis of the Pre-S1, Pre-S2, and S regions. The frequency of mutations in the S gene was significantly higher among those older than 50 years (mean 8.5 vs. 5.4 mutations per subject, p = 0.03). Twelve patients (50%) had mutations in the 'α' determinant region of the S gene. Mutations at amino acid position 126 were most common in eight subjects. Three had a mutation at position 133. Only one patient had a mutation at position 145-the classic vaccine-escape mutation. Despite the universal HBV vaccination program, the vaccine-escape mutant is rare in our cohort of predominantly Asian patients.

The Emerging Role of Glucagon-Like Peptide-1 Receptor Agonists for the Treatment of Metabolic Dysfunction-Associated Steatohepatitis.

Metabolic dysfunction-associated steatotic liver disease (MASLD) affects 1 in 3-4 adult individuals and can progress to metabolic dysfunction-associated steatohepatitis (MASH) and cirrhosis. Insulin resistance plays a central role in MASLD/MASH pathophysiology with higher rates of MASLD (2 in 3) and MASH with fibrosis (1 in 5) in adults with obesity and diabetes. This review summarizes the role of glucagon-like peptide-1 receptor agonists in treating MASLD/MASH. Although not approved by the Food and Drug Administration for the treatment of MASLD, this class of medication is available to treat obesity and type 2 diabetes and has been shown to reverse steatohepatitis, reduce cardiovascular risk, and is safe to use across the spectrum of MASLD with or without fibrosis.

Human monkeypox: An updated appraisal on epidemiology, evolution, pathogenesis, clinical manifestations, and treatment strategies.

Monkeypox (Mpox) is a zoonotic viral disease caused by the monkeypox virus (MPXV), a member of the Orthopoxvirus genus. The recent occurrence of Mpox infections has become a significant global issue in recent months. Despite being an old disease with a low mortality rate, the ongoing multicountry outbreak is atypical due to its occurrence in nonendemic countries. The current review encompasses a comprehensive analysis of the literature pertaining to MPXV, with the aim of consolidating the existing data on the virus's epidemiological, biological, and clinical characteristics, as well as vaccination and treatment regimens against the virus.

Evolutionary History and Genetic Variation of Zika Virus: Connection Between Thailand Zika Viruses and Global Outbreaks Strains.

Background: Zika virus (ZIKV) has significant potential to cause future outbreaks due to insufficient countermeasures. The evolution of ZIKV in Southeast Asian countries remains poorly understood. Materials and Methods: The phylogenetic, phylogeographic network, and recombination analyses of 366 ZIKV complete genome sequences identified between 1947 and 2021 were performed and the amino acid variation landscape was determined to reveal the evolutionary characteristics. Results: ZIKV falls into two major genogroups: GI and GII, segregated into further subgenogroups (GI-1 to GI-3) and (GII-1 to GII-3), respectively. Importantly, Thailand strains cluster with Southeast Asian outbreak strains (Singapore 2016, the Philippines 2012, Cambodia 2010) into GII-2 and form a lineage independent of French Polynesia and the Americas large outbreak strains. Thailand ZIKV strains shared their ancestral route to the strains from French Polynesia, which further connects to Brazil ZIKV through a short mutational branch. Both recombination and specific mutations may contribute to the emergence of new virus lineage in Thailand. Conclusion: This report provides insights into the evolutionary characteristics of ZIKV in Southeast Asia, which may be helpful for epidemiological investigation, vaccine development, and surveillance of the virus.

NSAIDs do not reduce severity among post-ERCP pancreatitis patients.

OBJECTIVE: Non-steroidal anti-inflammatory drugs (NSAIDs) are the most studied chemoprophylaxis for post-endoscopic retrograde cholangiopancreatography pancreatitis (PEP). While previous systematic reviews have shown NSAIDs reduce PEP, their impact on moderate to severe PEP (MSPEP) is unclear. We conducted a systematic review and meta-analysis to understand the impact of NSAIDs on MSPEP among patients who developed PEP. We later surveyed physicians' understanding of that impact. DESIGN: A systematic search for randomized trials using NSAIDs for PEP prevention was conducted. Pooled-prevalence and Odds-ratio of PEP, MSPEP were compared between treated vs. control groups. Analysis was performed using R software. Random-effects model was used for all variables. Physicians were surveyed via email before and after reviewing our results. RESULTS: 7688 patients in 25 trials were included. PEP was significantly reduced to 0.598 (95%CI, 0.47-0.76) in the NSAIDs group. Overall burden of MSPEP was reduced among all patients undergoing ERCP: OR 0.59 (95%CI, 0.42-0.83). However, NSAIDs didn't affect the proportion of MSPEP among those who developed PEP (p = 0.658). Rectal Indomethacin and diclofenac reduced PEP but not MSPEP. Efficacy didn't vary by risk, timing of administration, or bias-risk. Survey revealed a change in the impression of the effect of NSAIDs on MSPEP after reviewing our results. CONCLUSIONS: Rectal diclofenac or indomethacin before or after ERCP reduce the overall burden of MSPEP by reducing the pool of PEP from which it can arise. However, the proportion of MSPEP among patients who developed PEP is unaffected. Therefore, NSAIDs prevent initiation of PEP, but do not affect severity among those that develop PEP. Alternative modalities are needed to reduce MSPEP among patients who develop PEP.

Genetic characteristics and geographic distribution of rabies virus in China.

China is one of the largest countries with endemic rabies. In this study, we examined the full-length genome sequences of 87 rabies virus (RABV) strains identified in China from 1931 to 2019. Chinese RABV isolates were divided into two major clades, GI and GII. Clade GI consisted of viruses from the Asian clade, which was further divided into three subclades: Asian1, Asian2, and Asian3. Clade GII consisted of viruses from the Cosmopolitan, Arctic-related, and Indian clades. A phylogeographic network showed that the variation of rabies virus was more closely associated with geographic location than with the host species. Recombination appears to be one of the factors driving the emergence of new viral strains.

Duck hepatitis a virus: Full-length genome-based phylogenetic and phylogeographic view during 1986-2020.

Duck hepatitis A virus (DHAV) is one of key pathogens for duck viral hepatitis, especially in Asian duck industry. Currently, two main genotypes (DHAV-1 and -3) exist. To explore insightfully the evolutionary character, we assessed the available 141 full-length genome sequences of DHAV isolated in 1986-2020 globally and divided DHAV-1 and DHAV-3 into further seven (DHAV-1 a-g) and five (DHAV-3 a-e) sub-clades, respectively. Phylogenetic and phylogeographic network analyses indicated great genetic diversity of DHAV identified in China, where the DHAV-1 cluster and DHAV-3 cluster were linked by virus strain HDHV1-BJ (GenBank ID: FJ157172.1) and Du_CH_LSD_090612 (GenBank ID: JF828995.1) via a long mutational branch and intermediate strains. Several strains previously identified as DHAV-1 according to the partial gene sequences were actually clustered within DHAV-3 in full-length genome-based analysis. Furthermore, we identified 32 recombination events across virus genome with the recombination hotspot at the 5' end and upstream of the capsid coding region. The highest variability of DHAV polyprotein was shown at the upstream region of the N terminus P-loop region, e.g., amino acids 672-716, followed by the aa 334-359 in the Capsid encoding region. The results presented here provides a robust insight into the genetic exchange patterns of DHAV genomes during the past decades, which may be used to map the evolutionary history and facilitate preventive measures of DHAVs.

Classification of Parkinson's Disease in Patch-Based MRI of Substantia Nigra.

Parkinson's disease (PD) is a chronic and progressive neurological disease that mostly shakes and compromises the motor system of the human brain. Patients with PD can face resting tremors, loss of balance, bradykinesia, and rigidity problems. Complex patterns of PD, i.e., with relevance to other neurological diseases and minor changes in brain structure, make the diagnosis of this disease a challenge and cause inaccuracy of about 25% in the diagnostics. The research community utilizes different machine learning techniques for diagnosis using handcrafted features. This paper proposes a computer-aided diagnostic system using a convolutional neural network (CNN) to diagnose PD. CNN is one of the most suitable models to extract and learn the essential features of a problem. The dataset is obtained from Parkinson's Progression Markers Initiative (PPMI), which provides different datasets (benchmarks), such as T2-weighted MRI for PD and other healthy controls (HC). The mid slices are collected from each MRI. Further, these slices are registered for alignment. Since the PD can be found in substantia nigra (i.e., the midbrain), the midbrain region of the registered T2-weighted MRI slice is selected using the freehand region of interest technique with a 33 × 33 sized window. Several experiments have been carried out to ensure the validity of the CNN. The standard measures, such as accuracy, sensitivity, specificity, and area under the curve, are used to evaluate the proposed system. The evaluation results show that CNN provides better accuracy than machine learning techniques, such as naive Bayes, decision tree, support vector machine, and artificial neural network.

Genetic Characteristics and Phylogeographic Dynamics of Echovirus.

Echoviruses belong to the genus Enterovirus in the Picornaviridae family, forming a large group of Enterovirus B (EV-B) within the Enteroviruses. Previously, Echoviruses were classified based on the coding sequence of VP1. In this study, we performed a reliable phylogenetic classification of 277 sequences isolated from 1992 to 2019 based on the full-length genomes of Echovirus. In this report, phylogenetic, phylogeographic, recombination, and amino acid variability landscape analyses were performed to reveal the evolutional characteristics of Echovirus worldwide. Echoviruses were clustered into nine major clades, e.g., G1-G9. Phylogeographic analysis showed that branches G2-G9 were linked to common strains, while the branch G1 was only linked to G5. In contrast, strains E12, E14, and E16 clustered separately from their G3 and G7 clades respectively, and became a separate branch. In addition, we identified a total of 93 recombination events, where most of the events occurred within the VP1-VP4 coding regions. Analysis of amino acid variation showed high variability in the a positions of VP2, VP1, and VP3. This study updates the phylogenetic and phylogeographic information of Echovirus and indicates that extensive recombination and significant amino acid variation in the capsid proteins drove the emergence of new strains.

Phylogeographic dynamics and molecular characteristics of Enterovirus 71 in China.

Enterovirus 71 (EV71) and coxsackievirus (CV-A16) are the major etiological agents of hand, foot and mouth disease (HFMD). This report reviewed the full-length genomic sequences of EV71 identified in different provinces of China between 1998 and 2019 (a total of 312) in addition to eight worldwide reference genomes to address the genomic evolution and genetic events. The main prevalent EV71 strians in China are C4 genotypes, co-circulating with a few A, B5, C1, and C2 subgenotypes. A new emerging subgenotype in China was identified and classified as B6 genotype. Phylogeographic analysis revealed multiple branches, where a Jiangsu strain 2006-52-9 (GenBank ID: KP266579.1) was linked to different subgenotypes through multiple long mutant branches, including the CV-A16 viruses through the A genotype. Furthermore, identification of 28 natural recombination events suggests that the emergence of new genotypes are associated with intratypic recombination involving EV71 strains and intertypic recombination between EV71 and CV-A16 strains. Compared with the structural proteins, the non-structural proteins of EV71 seem to be highly variable with the highest variable regions of peptidase C3 (3C protein), P2A, and the N-terminus of RNA-dependent RNA polymerase. This study updates the phylogenetic and phylogeographic information of EV71 and provides clues to the emergence of new genotypes of EV71 based on genetics.

Multiple potential recombination events among Newcastle disease virus genomes in China between 1946 and 2020.

Introduction: Newcastle Disease Virus (NDV) is a highly adaptable virus with large genetic diversity that has been widely studied for its oncolytic activities and potential as a vector vaccine. This study investigated the molecular characteristics of 517 complete NDV strains collected from 26 provinces across China between 1946-2020. Methods: Herein, phylogenetic, phylogeographic network, recombination, and amino acid variability analyses were performed to reveal the evolutionary characteristics of NDV in China. Results and discussions: Phylogenetic analysis revealed the existence of two major groups: GI, which comprises a single genotype Ib, and GII group encompassing eight genotypes (I, II, III, VI. VII. VIII, IX and XII). The Ib genotype is found to dominate China (34%), particularly South and East China, followed by VII (24%) and VI (22%). NDV strains from the two identified groups exhibited great dissimilarities at the nucleotide level of phosphoprotein (P), matrix protein (M), fusion protein (F), and haemagglutinin-neuraminidase (HN) genes. Consistently, the phylogeographic network analysis revealed two main Network Clusters linked to a possible ancestral node from Hunan (strain MH289846.1). Importantly, we identified 34 potential recombination events that involved mostly strains from VII and Ib genotypes. A recombinant of genotype XII isolated in 2019 seems to emerge newly in Southern China. Further, the vaccine strains are found to be highly involved in potential recombination. Therefore, since the influence of recombination on NDV virulence cannot be predicted, this report's findings need to be considered for the security of NDV oncolytic application and the safety of NDV live attenuated vaccines.

The phylogenetic and phylogeographic landscape of the beak and feather disease virus, 1996-2022.

The beak and feather disease virus (BFDV), causative agent of Psittacine beak and feather disease (PBFD), is a highly fatal and widespread virus that infects both the wild and captive Psittaciformes around the world. The BFDV genome is a ssDNA of approximately 2 kb in size, making it among the smallest known pathogenic viruses. Though, the virus is placed in Circoviridae family of the Circovirus genus, there is no classification system on clade and sub-clade level according to the International Committee on Taxonomy of Viruses and the strains are grouped on the bases of geographic locations. Thus, we provide the latest and robust phylogenetic classification of BFDVs in this study based on full-length genomic sequences, grouping all the available 454 strains detected during 1996-2022 into two distinct clades, e.g., GI and GII. The GI clade is further divided into six sub-clades (GI a-f), while GII into two sub-clades (GII a and b). In addition, the phylogeographic network identified high variability among the BFDV strains, showing several branches, where all the branches are connected to four strains, e.g., BFDV-ZA-PGM-70A(GenBank ID: HM748921.1, 2008-South Africa), BFDV-ZA-PGM-81A(GenBank ID: JX221009.1, 2008-South Africa), BFDV14(GenBank ID: GU015021.1, 2010-Thailand) and BFDV-isolate-9IT11(GenBank ID: KF723390.1, 2014-Italy). Furthermore, we identified 27 recombination events in the rep (replication-associated protein) and cap (capsid protein) coding regions using the complete genomes of BFDVs. Similarly, the amino acids variability analysis indicated that both the rep and cap regions are highly variable with values exceeding the variability coefficient estimation limit of 1.00, speculating the possible amino acids drift with the emergence of new strains. The findings provided in this study may offer the latest phylogenetic, phylogeographic and evolutionary landscape of the BFDVs.

Genetic comparison of transmissible gastroenteritis coronaviruses.

Transmissible gastroenteritis virus (TGEV) is a porcine coronavirus that threatens animal health and remains elusive despite years of research efforts. The systematical analysis of all available full-length genomes of TGEVs (a total of 43) and porcine respiratory coronaviruses PRCVs (a total of 7) showed that TGEVs fell into two independent evolutionary phylogenetic clades, GI and GII. Viruses circulating in China (until 2021) clustered with the traditional or attenuated vaccine strains within the same evolutionary clades (GI). In contrast, viruses latterly isolated in the USA fell into GII clade. The viruses circulating in China have a lower similarity with that isolated latterly in the USA all through the viral genome. In addition, at least four potential genomic recombination events were identified, three of which occurred in GI clade and one in GII clade. TGEVs circulating in China are distinct from the viruses latterly isolated in the USA at either genomic nucleotide or antigenic levels. Genomic recombination serves as a factor driving the expansion of TGEV genomic diversity.

Genetic Characteristics and Phylogeographic Dynamics of Lagoviruses, 1988-2021.

Rabbit haemorrhagic disease virus (RHDV), European brown hare syndrome virus (EBHSV), rabbit calicivirus (RCV), and hare calicivirus (HaCV) belong to the genus Lagovirus of the Caliciviridae family that causes severe diseases in rabbits and several hare (Lepus) species. Previously, Lagoviruses were classified into two genogroups, e.g., GI (RHDVs and RCVs) and GII (EBHSV and HaCV) based on partial genomes, e.g., VP60 coding sequences. Herein, we provide a robust phylogenetic classification of all the Lagovirus strains based on full-length genomes, grouping all the available 240 strains identified between 1988 and 2021 into four distinct clades, e.g., GI.1 (classical RHDV), GI.2 (RHDV2), HaCV/EBHSV, and RCV, where the GI.1 clade is further classified into four (GI.1a-d) and GI.2 into six sub-clades (GI.2a-f). Moreover, the phylogeographic analysis revealed that the EBHSV and HaCV strains share their ancestor with the GI.1, while the RCV shares with the GI.2. In addition, all 2020-2021 RHDV2 outbreak strains in the USA are connected to the strains from Canada and Germany, while RHDV strains isolated in Australia are connected with the USA-Germany haplotype RHDV strain. Furthermore, we identified six recombination events in the VP60, VP10, and RNA-dependent RNA polymerase (RdRp) coding regions using the full-length genomes. The amino acid variability analysis showed that the variability index exceeded the threshold of 1.00 in the ORF1-encoded polyprotein and ORF2-encoded VP10 protein, respectively, indicating significant amino acid drift with the emergence of new strains. The current study is an update of the phylogenetic and phylogeographic information of Lagoviruses that may be used to map the evolutionary history and provide hints for the genetic basis of their emergence and re-emergence.

Characterization of HBV surface antigen isoforms in the natural history and treatment of HBV infection.

BACKGROUND: The loss of HBV HBsAg or functional cure is a desirable goal of hepatitis B management. The relative abundances of HBsAg isoforms may offer additional diagnostic and predicting values. To evaluate the clinical utility of HBsAg isoforms, we developed novel prototype assays on the ARCHITECT automated serology platform that specifically detects total-HBsAg (T-HBsAg), large (L-HBsAg), and middle (M-HBsAg) products of the S gene to determine the isoform composition of human specimens from acute and chronic HBV infection and during long-term nucleos(t)ide analog therapy. RESULTS: In the early phase of acute HBV infection, L-HBsAg and M-HBsAg emerged within days and were in parallel to T-HBsAg during the entire course of infection. M-HBsAg levels were consistently higher than L-HBsAg levels. Patients with HBeAg(+) chronic hepatitis B had higher T-HBsAg, M-HBsAg, and L-HBsAg levels compared with HBeAg(-) patients. Correlations of M-HBsAg and L-HBsAg to T-HBsAg were similar in both. In contrast, there was no strong correlation between L-HBsAg or M-HBsAg with HBV DNA levels. During long-term nucleos(t)ide analog treatment, changes in HBsAg isoform abundance were proportional to T-HBsAg regardless of treatment responses for both HBeAg(+) and HBeAg(-) chronic hepatitis B. A larger sample size may be necessary to detect a significant difference. CONCLUSION: HBsAg isoform compositions parallel T-HBsAg levels in both acute and chronic hepatitis B infection. L-HBsAg and M-HBsAg individual biomarkers do not appear to provide an additional diagnostic benefit for staging chronic disease or monitoring response to treatment with current therapies.

Genetic diversity, distribution, and evolution of chicken anemia virus: A comparative genomic and phylogenetic analysis.

Chicken infectious anemia (CIA) is an immunosuppressive poultry disease that causes aplastic anemia, immunosuppression, growth retardation and lymphoid tissue atrophy in young chickens and is responsible for huge economic losses to the poultry industry worldwide. The disease is caused by the chicken anemia virus (CAV), which belongs to the genus Gyrovirus, family Anelloviridae. Herein, we analyzed the full-length genomes of 243 available CAV strains isolated during 1991-2020 and classified them into two major clades, GI and GII, divided into three and four sub-clades, GI a-c, and GII a-d, respectively. Moreover, the phylogeographic analysis revealed that the CAVs spread from Japan to China, China to Egypt and subsequently to other countries, following multiple mutational steps. In addition, we identified eleven recombination events within the coding and non-coding regions of CAV genomes, where the strains isolated in China were the most active and involved in ten of these events. Furthermore, the amino acids variability analysis indicated that the variability coefficient exceeded the estimation limit of 1.00 in VP1, VP2, and VP3 proteins coding regions, demonstrating substantial amino acid drift with the rise of new strains. The current study offers robust insights into the phylogenetic, phylogeographic and genetic diversity characteristics of CAV genomes that may provide valuable data to map the evolutionary history and facilitate preventive measures of CAVs.

IoMT-Enabled Computer-Aided Diagnosis of Pulmonary Embolism from Computed Tomography Scans Using Deep Learning.

The Internet of Medical Things (IoMT) has revolutionized Ambient Assisted Living (AAL) by interconnecting smart medical devices. These devices generate a large amount of data without human intervention. Learning-based sophisticated models are required to extract meaningful information from this massive surge of data. In this context, Deep Neural Network (DNN) has been proven to be a powerful tool for disease detection. Pulmonary Embolism (PE) is considered the leading cause of death disease, with a death toll of 180,000 per year in the US alone. It appears due to a blood clot in pulmonary arteries, which blocks the blood supply to the lungs or a part of the lung. An early diagnosis and treatment of PE could reduce the mortality rate. Doctors and radiologists prefer Computed Tomography (CT) scans as a first-hand tool, which contain 200 to 300 images of a single study for diagnosis. Most of the time, it becomes difficult for a doctor and radiologist to maintain concentration going through all the scans and giving the correct diagnosis, resulting in a misdiagnosis or false diagnosis. Given this, there is a need for an automatic Computer-Aided Diagnosis (CAD) system to assist doctors and radiologists in decision-making. To develop such a system, in this paper, we proposed a deep learning framework based on DenseNet201 to classify PE into nine classes in CT scans. We utilized DenseNet201 as a feature extractor and customized fully connected decision-making layers. The model was trained on the Radiological Society of North America (RSNA)-Pulmonary Embolism Detection Challenge (2020) Kaggle dataset and achieved promising results of 88%, 88%, 89%, and 90% in terms of the accuracy, sensitivity, specificity, and Area Under the Curve (AUC), respectively.